`Bandits.ArrayModel.reward_ae_eq_cond`🔗

Lemma

No docstring.

theorem

Bandits.ArrayModel.reward_ae_eq_cond.{u_1, u_2} {𝓐 : Type u_1}
  {R : Type u_2} {m𝓐 : MeasurableSpace 𝓐} {mR : MeasurableSpace R}
  [Nonempty 𝓐] [StandardBorelSpace 𝓐] [DecidableEq 𝓐] [Countable 𝓐]
  (alg : Learning.Algorithm 𝓐 R) (ν : ProbabilityTheory.Kernel 𝓐 R)
  (a : 𝓐) (n m : ℕ) :
  reward alg
      (n +
        1) =ᵐ[(arrayMeasure
        ν)[|(fun ω =>
          (action alg (n + 1) ω,
            Learning.pullCount (action alg) (action alg (n + 1) ω)
              (n + 1) ω)) ⁻¹'
        {(a, m)}]]
    fun ω => Prod.snd ω m a
Bandits.ArrayModel.reward_ae_eq_cond.{u_1,
    u_2}
  {𝓐 : Type u_1} {R : Type u_2}
  {m𝓐 : MeasurableSpace 𝓐}
  {mR : MeasurableSpace R} [Nonempty 𝓐]
  [StandardBorelSpace 𝓐] [DecidableEq 𝓐]
  [Countable 𝓐]
  (alg : Learning.Algorithm 𝓐 R)
  (ν : ProbabilityTheory.Kernel 𝓐 R)
  (a : 𝓐) (n m : ℕ) :
  reward alg
      (n +
        1) =ᵐ[(arrayMeasure
        ν)[|(fun ω =>
          (action alg (n + 1) ω,
            Learning.pullCount
              (action alg)
              (action alg (n + 1) ω)
              (n + 1) ω)) ⁻¹'
        {(a, m)}]]
    fun ω => Prod.snd ω m a

Code

lemma reward_ae_eq_cond (alg : Algorithm 𝓐 R) (ν : Kernel 𝓐 R) (a : 𝓐) (n m : ℕ) :
    reward alg (n + 1) =ᵐ[(arrayMeasure ν)[|(fun ω ↦ (action alg (n + 1) ω,
        pullCount (action alg) (action alg (n + 1) ω) (n + 1) ω)) ⁻¹' {(a, m)}]]
      (fun ω ↦ ω.2 m a)

Proof

by
  rw [reward_eq]
  refine ae_cond_of_forall_mem ?_ ?_
  · have : Measurable fun ω ↦ pullCount (action alg) (action alg (n + 1) ω) (n + 1) ω := by
      change Measurable ((fun p : (probSpace 𝓐 R) × 𝓐 ↦ pullCount (action alg) p.2 (n + 1) p.1) ∘
        (fun ω : probSpace 𝓐 R ↦ (ω, action alg (n + 1) ω)))
      exact (measurable_uncurry_pullCount (by fun_prop) _).comp (by fun_prop)
    exact (measurableSet_singleton _).preimage (by fun_prop)
  intro ω hω
  simp only [Set.mem_preimage, Set.mem_singleton_iff, Prod.mk.injEq] at hω
  simp only [hω.2]
  simp [hω.1]

Actions: Source · Open Issue

Meaning last changed in v4.34.0-rc2-1-g439785b (2026-08-23), the 5th recorded change.

Self-contained, with its dependencies inlined and proofs replaced by sorry: download the raw file · open it in the Lean web editor.

Dependency graph

Audit surface: 14 project declarations, 99 external constants

✓ Proved: no sorry anywhere in its closure

This is the tool's own reading of one build's recorded axioms, and it is not robust against an author who wants it to pass. Checking meant to be relied on should go through Comparator, which replays the proof through the kernel from an export against an explicit list of permitted axioms.

Bandits.ArrayModel.reward_ae_eq_cond🔗

`Bandits.ArrayModel.reward_ae_eq_cond`🔗